# Video Summarization Metric Evaluation on MLVU VS Eval Source: [Video Summarization Metric Evaluation on MLVU VS Eval]() Collection index: [llms.txt]() Data updated: 2026-04-28T09:38:22.055Z Evaluation of video summarization metrics, including Kendall's tau variants and Spearman's rho, performed on the MLVU VS Eval dataset. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Video Summarization Metric Evaluation | | Dataset (including any stated split) | MLVU VS Eval | | Metric | Kendall's tau\_b | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 13 of 13 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Kendall's tau\_b](): Higher is better; unit: SCALAR. - [Kendall's tau\_c](): Higher is better; unit: SCALAR. - [Spearman's rho](): Higher is better; unit: SCALAR. ## Recorded results | Method | Kendall's tau\_b | Result date | Report paper | | --- | --- | --- | --- | | QEVA | 0.6465 | Not recorded | 69f03f2f55a3c32af89fa1df | | Video-LMM Judge | 0.5376 | Not recorded | 69f03f2f55a3c32af89fa1df | | MLVU | 0.5284 | Not recorded | 69f03f2f55a3c32af89fa1df | | METEOR | 0.2663 | Not recorded | 69f03f2f55a3c32af89fa1df | | CIDEr | 0.2401 | Not recorded | 69f03f2f55a3c32af89fa1df | | SPICE | 0.2287 | Not recorded | 69f03f2f55a3c32af89fa1df | | BLEU-4 | 0.2113 | Not recorded | 69f03f2f55a3c32af89fa1df | | BLEU-3 | 0.1994 | Not recorded | 69f03f2f55a3c32af89fa1df | | BERTscore | 0.1415 | Not recorded | 69f03f2f55a3c32af89fa1df | | ROUGE-L | 0.1094 | Not recorded | 69f03f2f55a3c32af89fa1df | | BLEU-2 | 0.0673 | Not recorded | 69f03f2f55a3c32af89fa1df | | Video-Summary Similarity | 0.0278 | Not recorded | 69f03f2f55a3c32af89fa1df | | BLEU-1 | 0.0217 | Not recorded | 69f03f2f55a3c32af89fa1df | ### QEVA Kendall's tau\_b: 0.6465. Result ID: 69f07ffa47f34ce924d6cf3f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Direction":"QA-based","Reference Summary":"No","Video Used":"Yes"}. This record does not assert independent reproduction. ### Video-LMM Judge Kendall's tau\_b: 0.5376. Result ID: 69f07ffa47f34ce924d6cf3e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Direction":"LLM-based","Reference Summary":"No","Video Used":"Yes"}. This record does not assert independent reproduction. ### MLVU Kendall's tau\_b: 0.5284. Result ID: 69f07ffa47f34ce924d6cf3d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Direction":"LLM-based","Reference Summary":"Yes","Video Used":"No"}. This record does not assert independent reproduction. ### METEOR Kendall's tau\_b: 0.2663. Result ID: 69f07ffa47f34ce924d6cf38. [Reporting paper]() Recorded evaluation configuration: {"Direction":"Similarity-based","Reference Summary":"Yes","Video Used":"No"}. This record does not assert independent reproduction. ### CIDEr Kendall's tau\_b: 0.2401. Result ID: 69f07ffa47f34ce924d6cf39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Direction":"Similarity-based","Reference Summary":"Yes","Video Used":"No"}. This record does not assert independent reproduction. ### SPICE Kendall's tau\_b: 0.2287. Result ID: 69f07ffa47f34ce924d6cf3a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Direction":"Similarity-based","Reference Summary":"Yes","Video Used":"No"}. This record does not assert independent reproduction. ### BLEU-4 Kendall's tau\_b: 0.2113. Result ID: 69f07ffa47f34ce924d6cf36. [Reporting paper]() Recorded evaluation configuration: {"Direction":"Rule-based","Reference Summary":"Yes","Video Used":"No"}. This record does not assert independent reproduction. ### BLEU-3 Kendall's tau\_b: 0.1994. Result ID: 69f07ffa47f34ce924d6cf35. [Reporting paper]() Recorded evaluation configuration: {"Direction":"Rule-based","Reference Summary":"Yes","Video Used":"No"}. This record does not assert independent reproduction. ### BERTscore Kendall's tau\_b: 0.1415. Result ID: 69f07ffa47f34ce924d6cf3b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Direction":"Similarity-based","Reference Summary":"Yes","Video Used":"No"}. This record does not assert independent reproduction. ### ROUGE-L Kendall's tau\_b: 0.1094. Result ID: 69f07ffa47f34ce924d6cf37. [Reporting paper]() Recorded evaluation configuration: {"Direction":"Rule-based","Reference Summary":"Yes","Video Used":"No"}. This record does not assert independent reproduction. ### BLEU-2 Kendall's tau\_b: 0.0673. Result ID: 69f07ffa47f34ce924d6cf34. [Reporting paper]() Recorded evaluation configuration: {"Direction":"Rule-based","Reference Summary":"Yes","Video Used":"No"}. This record does not assert independent reproduction. ### Video-Summary Similarity Kendall's tau\_b: 0.0278. Result ID: 69f07ffa47f34ce924d6cf3c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Direction":"Similarity-based","Reference Summary":"No","Video Used":"Yes"}. This record does not assert independent reproduction. ### BLEU-1 Kendall's tau\_b: 0.0217. Result ID: 69f07ffa47f34ce924d6cf33. [Reporting paper]() Recorded evaluation configuration: {"Direction":"Rule-based","Reference Summary":"Yes","Video Used":"No"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.